Modeling Patient Care Trajectories with Transformer Hawkes Processes
This work addresses the problem of predicting patient care needs for healthcare providers, but it is incremental as it builds on existing methods.
The authors tackled the challenge of modeling irregular patient healthcare event trajectories by extending the Transformer Hawkes Process framework with an imbalance-aware training strategy, resulting in improved performance and clinically meaningful insights for identifying high-risk populations.
Patient healthcare utilization consists of irregularly time-stamped events, such as outpatient visits, inpatient admissions, and emergency encounters, forming individualized care trajectories. Modeling these trajectories is crucial for understanding utilization patterns and predicting future care needs, but is challenging due to temporal irregularity and severe class imbalance. In this work, we build on the Transformer Hawkes Process framework to model patient trajectories in continuous time. By combining Transformer-based history encoding with Hawkes process dynamics, the model captures event dependencies and jointly predicts event type and time-to-event. To address extreme imbalance, we introduce an imbalance-aware training strategy using inverse square-root class weighting. This improves sensitivity to rare but clinically important events without altering the data distribution. Experiments on real-world data demonstrate improved performance and provide clinically meaningful insights for identifying high-risk patient populations.